文章摘要
周 璇,陈光雄,赵 鑫.基于经验模式分解和神经网络的车轮踏面擦伤检测方法[J].润滑与密封,2015,40(6):13-18
基于经验模式分解和神经网络的车轮踏面擦伤检测方法
  
DOI:10.3969/j.issn.0254-0150.2015.05.003
中文关键词: 经验模式分解  神经网络  峭度  轮轨踏面擦伤
英文关键词: empirical mode decomposition  artificial neural networks  kurtosis  wheel tread flat
基金项目:国家自然科学基金项目(51275429).
作者单位E-mail
周 璇 西南交通大学牵引动力国家重点实验室摩擦学研究所 605858403@qq.com 
陈光雄 西南交通大学牵引动力国家重点实验室摩擦学研究所  
赵 鑫 西南交通大学牵引动力国家重点实验室摩擦学研究所  
摘要点击次数: 796
全文下载次数: 0
中文摘要:
      车轮踏面擦伤故障信号具有非平稳特性,为识别车轮踏面擦伤,提出一种将经验模式分解(Empirical Mode Decomposition)与神经网络相结合的诊断方法,通过实验获取车轮踏面擦伤故障信号,对故障信号EMD分解得到本征模函数分量(Intrinsic Mode Function,IMF),再对各阶IMF分量提取能量和峭度特征,构建出特征向量并输入到神经网络中进行故障识别。将此法通过LabVIEW编程实现并经实验验证,该方法在车速0~200 km/h时具有较高识别能力,与传统方法相比具有使用范围广,实用价值高的特点。
英文摘要:
      The wheel thread flat fault signals is non-stationary signals.To identify the wheel thread flat,a new fault diagnosis method was put forward,which combined the Empirical Mode Decomposition(EMD)with Artificial Neural Networks(ANNs).The wheel thread flat fault signals were collected by experimental tests and were analyzed using EMD to get the Intrinsic Mode Function(IMF)components.The energy and kurtosis features of these IMF components were extracted to construct the feature vector which was served as input parameters of the neural network to identify the fault pattern of the wheel/rail system.This identification procedure was implemented with LabVIEW and was verified by experiments.The experimental result shows that this method can effectively identify the wheel tread flat fault in the wheelset speed range of 0~200 km/h,and has a wider range of application.
查看全文   查看/发表评论  下载PDF阅读器
关闭

分享按钮